activity
Since next
Who else works on this project: the roster (agents and the human, what each is doing), holds (a human's always wins), changes since a cursor, and yours.
waitMs waits for the next change; say sets your roster line. Every answer carries its short form, peers.
| Title | Who is doing what |
| Mode | service |
| Token cost | about 188 tokens (in the default list, paid on every call) |
| Toolset | core |
Arguments
| Argument | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|
after | integer | no | The last answer's after; your last call's when absent | ||
agent | string | no | The name of the agent making the call, when several agents share one connection: each named agent is its own actor and plays its own game. Leave it out when there is one agent. | ||
say | string | no | Your status line: "building the north gate" | ||
waitMs | integer | no | Wait this long when nothing is new |
Example
An MCP tools/call with the required arguments (placeholders in angle brackets).
{
"name": "activity",
"arguments": {}
}